Las Vegas – Automotive industry leader STRADVISION has announced that its award-winning SVNet software is now available for use with Texas Instruments’ TDA4 automotive processor. This software, which uses deep learning-based technology to power the perception systems in ADAS (advanced driver assistance systems) and autonomous vehicles, enables external vehicle perception through 18+ platforms, including the TI processor platform. This means it can detect and recognize many objects, even in challenging lighting or weather conditions. SVNet was the first deep neural network to use the TDA2SX processor for deep learning-based object detection software, and it now also works with the TI TDA4VM processor family.
The implementation of SVNet on the TDA4 processor is optimized for both high performance and low power consumption, as well as a reduced bill of materials. This flexibility is crucial in today’s ADAS market and enables the wider mass-market production of Level 2 systems by automotive OEMs. Aish Dubey, General Manager of Automotive Processors at TI, commented on the partnership: “Enabling more cars on the road with advanced driver assistance capabilities can lead to greater driver comfort and improved road safety. The hardware-optimized SVNet software allows automotive designers to leverage our automotive system-on-chip products to enable surround-view vision, helping them improve the driver experience and road safety.”
STRADVISION CEO Junhwan Kim added: “The software for TI’s automotive processor is optimized for ADAS, and we will strive to lead the ADAS industry market trend of going beyond Level 2. At STRADVISION, our goals have always been ambitious, and the next step in our journey is providing a vision solution for OEM mass production that meets key performance requirements for Level 2 and the next level.” TI’s TDA4 processor family is designed for high-volume Level 2 ADAS applications and beyond, and is well-suited for a range of industrial applications including ADAS, robotics, machine vision, and radar sensing thanks to its combination of high-performance computing, deep-learning capabilities, and specialized accelerators for signal and image processing.
